Spam Reviews Research Articles

Ensemble Machine Learning Model for Classification of Spam Product Reviews

Nowadays, online product reviews have been at the heart of the product assessment process for a company and its customers. They give feedback to a company on improving product quality, planning, and monitoring its business schemes in order to increase sale and gain more profit. They are also helpful for customers to select the right products in less effort and time. Most companies make spam reviews of products in order to increase the products sales and gain more profit. Detecting spam product reviews is a challenging issue in NLP (natural language processing). Numerous machine learning approaches have attempted to detect and classify the product reviews as spam or nonspam. However, in order to improve the classification accuracy, this study has introduced an ensemble machine learning model that combines predictions from multilayer perceptron (MLP), K-Nearest Neighbour (KNN), and Random Forest (RF) and predicts the outcome of the review as spam or real (nonspam), based on the majority vote of the contributing models. In order to accomplish the task of spam review classification, the proposed ensemble and other benchmark boosting approaches are tested with 25 statistical features extracted from mobile application reviews of Yelp Dataset. Then, three different selection techniques are exploited to diminish the feature space and filter out the top 10 optimal features. The effectiveness of the proposed ensemble, the individual models, and other benchmark boosting approaches is again evaluated with 10 optimal features in terms of classification accuracy. Experimental outcomes illustrate that the proposed ensemble model outperformed the individual classifiers (MLP, KNN, and RF) and state-of-the-art boosting approaches like Generalized Boost Regression Model (GBM), Extreme Gradient Boost (XGBoost), and AdaBoost Regression Model in terms of classification accuracy.

Detection of Fake Reviews Using Group Model

Reviews of product or stores exist extensively in online e-commerce platform which is important for customers to make decisions. For economic reasons some dishonest people are employed to write fake reviews which is also called “opinion spamming” to promote or demote target products and services. Previous researches have made use of text similarity, linguistics, rating patterns, graph relationship and other behaviors for spammer detection. They mainly utilized product review list while it is difficult to find fake reviews by glancing over product reviews in time-descending order. Meanwhile there exists lots of useful information in the list of reviews of reviewers and relationships between reviewers when reviewers commonly reviewed the same stores. We propose the concept of review group and to the best of our knowledge, it’s the first time the review group concept is proposed and used. Review grouping algorithm is designed to effectively split reviews of reviewer into groups which participate in building novel grouping models to identify both positive and negative deceptive reviews. Several new features which are language independent based on group model are constructed. Additionally, we explore the collusion relationship between reviewers to build reviewer group collusion model. Evaluations show that the review group method and reviewer group collusion models can effectively improve the precision by 4%–7% compared to the baselines in fake reviews classification task especially when reviews are posted by professional review spammers.

A non-convex semi-supervised approach to opinion spam detection by ramp-one class SVM

Nowadays, e-commerce has become a part of our daily life in such a way that people's decision for buying products or choosing services highly depends on comments, reviews, and rates, which are posted on related businesses’ website and other social media. Because of the importance and prevalence of these sources of information, fraudsters are tempted to use fraudulently opinion sharing platforms in order to promote or to discredit some target products or services. Although a wide range of approaches have been proposed to address this problem and to help distinguish between the deceptive or fraudulent opinions from the trustful ones, this is still a challenging problem. Lack of well-defined deceptive data samples or insufficiency of spam review instances in the training sets cause supervised techniques facing an imbalanced classes problem. Furthermore, even in the golden normal opinion datasets, there is a possibility of the presence of some abnormal records or outliers. To deal with these two issues, we propose a robust and non-convex semi-supervised algorithm called “Ramp One-Class SVM”. In the proposed method, one-class SVM is adopted to handle the lack of labeled data for the deceptive opinions and by taking the advantages of non-convex properties of the Ramp loss function, we eliminate the effects of outliers and non-review opinions. The performance of the proposed method is evaluated by an artificial dataset and two real datasets including Ott and Yelp crowdsourced datasets. The results show the superiority of our method by achieving an accuracy of 92.13% and 74.37% for Ott and Yelp crowdsourced datasets, respectively. The obtained results also reveal the effectiveness of the proposed model in terms of precision, recall, generalization power, and robustness to the outliers.

Spam and Fake Spam Message Detection Framework Using Machine Learning Algorithm

Online reviews about the acquisition of items or administrations gave have become the primary wellspring of clients’ conclusions. So as to pick up benefit or acclaim, as a rule spam reviews are composed to advance or downgrade a couple of target items or administrations. This training is known as review spamming. In the previous barely any years, an assortment of strategies have been proposed so as to illuminate the issue of spam reviews. It is a mainstream correspondence and furthermore known as information trade media. Information could be of a book, numbers, figures or insights that are gotten to by a PC. These days, numerous individuals relies upon substance accessible in web-based social networking in their choices. Sharing of data with people groups has additionally pulled in social spammers to endeavor and spread spam messages to advance individual web logs, notices, advancements, phishing, trick, fakes, etc. The possibility that anyone will leave a review give a brilliant possibility for spammers to post spit audit with respect to item and administrations for different interests and possibilities. In this way, we propose a fake message detection system utilizing ML to recognize the spam and fake messages on the internet based life stage.

A Robust False Spam Review Detection Using Deep Long Short-Term Memory (LSTM) Based Recurrent Neural Network

Our day-to-day activity is highly influenced by development of Internet. One of the rapid growing area in Internet is E-commerce. People are eager to buy products from online sites like Amazon, embay, Flipkart etc. Customers can write reviews about the products purchased online. The purchasing of good through online has been increasing exponentially since last few years. As there is no physical contact with goods before purchasing through online, people totally rely on reviews about the product before purchasing it. Hence review plays an important role in deciding the quality of the product. There are many customers who give online reviews about the product after using it. Hence the quality of the product is decided by the reviews of the customers. Thus, detection of fake reviews has become one of the important task. The proposed system will help in finding such fake reviews about the product, so that the fake reviews can be eliminated. Therefore, the purchasing of the products will be totally based on the genuine reviews. The proposed system uses Deep Recurrent Neural Network (DRNN) to predict the fake reviews and the performance of the proposed method has compared with Naïve Bayes Algorithm. The proposed model shows good accuracy and can handle huge amount of data over the existing system.

A Survey on Feature Selection Based Spam Review Detection using Deep Learning Techniques

In recent times, online shoppers are technically knowledgeable and open to product reviews. They usually read the buyer reviews and ratings before purchasing any product from ecommerce website. For the better understanding of products or services, reviews provided by the customers gives the vital source of information. In order to buy the right products for the individuals and to make the business decisions for the Organization online reviews are very important. These reviews or opinions in turn, allow us to find out the strength and weakness of the products. Spam reviews are written in order to falsely promote or demote a few target products or services. Also, detecting the spam reviews has also become more critical issue for the customer to make good decision during the purchase of the product. A major problem in identifying the fake review detection is high dimensionality of the feature space. Therefore, feature selection is an essential step in the fake review detection to reduce dimensionality of the feature space and to improve the classification accuracy. Hence it is important to detect the spam reviews but the major issues in spam review detection are the high dimensionality of feature space which contains redundant, noisy and irrelevant features. To resolve this, Deep Learning Techniques for selecting features is necessary. To classify the features, classifiers such as Naive Bayes, K Nearest Neighbor are used. An analysis of the various techniques employed to identify false and genuine reviews has been surveyed.

Identifying ground truth in opinion spam: an empirical survey based on review psychology

Because it is very harmful, opinion spam, especially that involving untruthful reviews, has attracted much attention in the last decade. However, the lack of annotations, i.e., the ground truth problem, still serves as the key challenge. It is difficult because spammers always deliberately forge their reviews, which cannot be distinguished even by field experts. Considering the obvious intention of spammers, i.e., to promote or demote an items reputation, the opportunity exists to label them by considering crowd psychology. To date, several studies have applied, verified, and presented helpful evidence, including prior, empirical, heuristic, and simulative pseudo truths. In this paper, after investigating both authentic and deceptive reviewers’ diverse motives, we survey state-of-the-art truth by considering two classical roles, e.g., crowdsourcing and expert spammers. For each role, several topics related to spam attacks either with or without disguising and possible outliers are highlighted. Comparison analyses led to some interesting conclusions: 1) data on professional spammers are more challenging to collect and less reliable than data on crowdsourcing spammers; 2) most linguistic evidences are less reliable than behavioral footprints; 3) abnormal activities are as trustworthy as spamming objectives, while they hardly need any extra support, such as the user profile; and 4) the top reliable facts requiring acceptable effort are deviation, burstiness, grouped spamming, deviation over the threshold, review distribution, opinion proportion and spam cost. Moreover, we introduce several promising directions for future research. In general, this survey may shed light on new angles that can be used to understand review spam and to improve the performance of any anti-spam platforms.

An Empirical Approach to Predict Spam Reviews

An Empirical Approach to Predict Spam Reviews

ColluEagle: collusive review spammer detection using Markov random fields

Product reviews are extremely valuable for online shoppers in providing purchase decisions. Driven by immense profit incentives, fraudsters deliberately fabricate untruthful reviews to distort the reputation of online products. As online reviews become more and more important, group spamming, i.e., a team of fraudsters working collaboratively to attack a set of target products, becomes a new fashion. Previous works use review network effects, i.e. the relationships among reviewers, reviews, and products, to detect fake reviews or review spammers, but ignore time effects, which are critical in characterizing group spamming. In this paper, we propose a novel Markov random field (MRF)-based method (ColluEagle) to detect collusive review spammers, as well as review spam campaigns, considering both network effects and time effects. First we identify co-review pairs, a review phenomenon that happens between two reviewers who review a common product in a similar way, and then model reviewers and their co-review pairs as a pairwise-MRF, and use loopy belief propagation to evaluate the suspiciousness of reviewers. We further design a high quality yet easy-to-compute node prior for ColluEagle, through which the review spammer groups can also be subsequently identified. Experiments show that ColluEagle can not only detect collusive spammers with high precision, significantly outperforming state-of-the-art baselines --- FraudEagle and SpEagle, but also identify highly suspicious review spammer campaigns.

Recommendation of Distance Education Colleges to Students based on Alumni Feedback

Sentiment Analysis (SA) systems are very common because most people trust it based on the opinions, emotions, attitudes and feelings shared by the users for decision making purposes about the product, service, news analytics etc. Sentiment analysis or opinion mining is used to automatically detect and classify sentiments into positive, negative or neutral opinion on product or service through certain algorithms. The expeditious growth of internet leads to the increase of reviews about product, services, movies, restaurants or vacation destinations and organizations. In order to increase or decrease the market value of the product, spammers may give the fake ratings. Sentiment Analysis system face great difficulties in deploying the algorithms to classify each review as either honest review, posted by the customers after using the products, or spam review, posted by the individual spammer or spammer groups. Another major challenge faced by the sentiment analysis system is that it lacks the accuracy of predicting implicit and explicit features present in the dataset is low, which is the major challenge in opinion mining system. The proposed system deals with text pre-processing which helps in improving the overall performance of the sentiment analysis systems and an effective system is developed to identify the fake reviews present in the dataset. Association Rule Mining along with K-Means clustering is used to achieve higher efficiency in classification of implicit and explicit features. Lexicon method is used for the classification of sentiments into positive and negative polarities. The advantage of proposed system is that, it can identify and remove the fake reviews in the dataset and extraction of both implicit and explicit feature can be identified through Lexicon based Method along with its polarities.

A burst-based unsupervised method for detecting review spammer groups

With the development of e-commerce, online shopping has become a part of people's life. As customers often refer to online product reviews for shopping, sellers often collude with review spammers in writing fake reviews to promote or demote target products. In particular, spammers working in groups are more harmful than individual attacks. To detect such spammer groups, previous researchers proposed some frequent item mining based algorithms and graph-based algorithms. In this paper, we propose a method called GSDB (Group Spam Detection algorithm based on review Burst). Our algorithm first locates target products attacked by spammers by detecting the abnormality of product rating distribution. As group spammers usually post many fake reviews within a short period, we design a burst-based algorithm that discovers candidate spammer groups in reviewbursts using the Kernel Density Estimation algorithm. As some innocent reviewers may coincidently review during the burst period, we formulate a variety of individual spam indicators to measure the spamicity of the reviewers to isolate the candidate spammer groups. Finally, we design a series of group spam indicators to measure and classify the spamicity of spammer groups. Experimental results show that our proposed GSDB algorithm outperforms state-of-the-art algorithms.

Spam review detection using LSTM autoencoder: an unsupervised approach

The review of online products or services is becoming a major factor in the user’s purchasing decisions. The popularity and influence of online reviews attract spammers who intend to elevate their products or services by writing positive reviews for them and lowering the business of others by writing negative reviews. Traditionally, the spam review identification task is seen as a two-class classification problem. The classification approach requires a labelled dataset to train a model for the environment it is working on. The unavailability of the labelled dataset is a major limitation in the classification approach. To overcome the problem of the labelled dataset, we propose an unsupervised learning model combining long short-term memory (LSTM) networks and autoencoder (LSTM-autoencoder) to distinguish spam reviews from other real reviews. The said model is trained to learn the patterns of real review from the review’s textual details without any label. The experimental results show that our model is able to separate the real and spam review with good accuracy.

LDA_RAD: A Spam review detection method based on topic model and reviewer anomaly degree

Online shopping has become a popular activity among consumers. Reviews have become important standards for consumers to buy things. To detect the spam re-views that do not correctly response the right information of goods, a method based on topic model and reviewer anomaly degree is raised. This method divides spam reviews into content-type and deceptive spam review respectively. Firstly, the experimental data set is modelled by LDA topic, which detects the content-type spam reviews with different themes. Then the deceptive spam reviews are detected by the reviewer’s abnormality degree index. It assigns a score to each review according to extracted features and related weights. A score is finally combined with an adaptive weight calculation based on the abnormal period and the reviewer’s similarity to obtain the review score. The review with a high score is considered to be a spam review, and the review with a low score is a true review. Experiments show that this method has a certain improvement on the recognition rate of spam reviews.

An Attention-Based Unsupervised Adversarial Model for Movie Review Spam Detection

With the prevalence of the Internet, online reviews have become a valuable information resource for people. However, the authenticity of online reviews remains a concern, and deceptive reviews have become one of the most urgent network security problems to be solved. Review spams will mislead users into making suboptimal choices and inflict their trust in online reviews. Most existing research manually extracted features and labeled training samples, which are usually complicated and time-consuming. This paper focuses primarily on a neglected emerging domain - movie review, and develops a novel unsupervised spam detection model with an attention mechanism. By extracting the statistical features of reviews, it is revealed that users will express their sentiments on different aspects of movies in reviews. An attention mechanism is introduced in the review embedding, and the conditional generative adversarial network is exploited to learn users' review style for different genres of movies. The proposed model is evaluated on movie reviews crawled from Douban, a Chinese online community where people could express their feelings about movies. The experimental results demonstrate the superior performance of the proposed approach.

Generating behavior features for cold-start spam review detection with adversarial learning

Due to the wide applications, spam detection has long been a hot research topic in both academia and industry. Existing studies show that behavior features are effective in distinguishing the spam and legitimate reviews. However, it usually takes a long time to collect such features and thus is hard to apply them to cold-start spam review detection tasks. Recent advances leveraged the neural network to encode the various types of textual, behavior, and attribute information for this task. However, the inherent problem, i.e., lack of effective behavior features for new users who post just one review, is still unsolved.In this paper, we exploit the generative adversarial network (GAN) for addressing this problem. The key idea is to generate synthetic behavior features (SBFs) for new users from their easily accessible features (EAFs). Specifically, we first select six well recognized real behavior features (RBFs) existing for regular users. We then train a GAN framework including a generator to generate SBFs from their EAFs including text, rating, and attribute features, and a discriminator to discriminate RBFs and SBFs. We design a new implementation of generator and discriminator for effective training. The trained GAN is finally applied to new users for generating synthetic behavior features. We conduct extensive experiments on two Yelp datasets. Experimental results demonstrate that our proposed framework significantly outperforms the state-of-the-art methods.

Spam Detector: A Solution for Finding Bogus Opinions and Spammer Classification in E-Commerce

In this paper we propose a system called Spam Detector to find out spam reviews of particular product. This framework uses spam features which helps to review datasets. In proposed system four different categories of features are included such as review behavioral (based on behaviour of review) , user behavioral (based on behaviour of user), review linguistic (based on linguistic pattern of review) and user linguistic (based on linguistic pattern of user). In today’s world, most of people take decision based on information available through social media reviews on a topic or product. Due to this it is possible that anyone can post a review for a particular product which give a chance for spammers to post junk reviews related to particular product and facilities. To find out such spammers and the spam review is becoming important. Some methods exist to cope up with this problem, but these methods hardly detect spam reviews, and are not based on the extracted feature type. Weight of spam features are used to gain better results in the form of different aspects tested on real world review datasets. Here the used dataset is from Amazon websites. The experimental results show that Spam Detector beats the present method.

Label propagation-based approach for detecting review spammer groups on e-commerce websites

Online product reviews are very important information resources on e-commerce websites and significantly influence consumers’ purchase decisions. Driven by interests, however, some merchants might hire a group of reviewers working together to promote or demote a set of target products by writing fake reviews. Such a collusive fraudulent reviewer group is generally termed a review spammer group and is more harmful to e-commerce websites than individual review spammers. To address this issue, in this paper we propose a label propagation-based approach to detect review spammer groups on e-commerce websites. First, based on the evaluation data of reviewers, we extract the associations between reviewers with respect to review time and product ratings to construct a relationship graph of reviewers. Second, we propose an improved label propagation algorithm with a propagation intensity and an automatic filtering mechanism to find candidate spammer groups based on the constructed reviewer relationship graph. Finally, we propose a ranking algorithm that combines the entropy method and the analytic hierarchy process to rank the candidate spammer groups and thus identify the top-k review spammer groups. The experimental results of the real-world Amazon and Yelp datasets show that the proposed approach performs better than the baseline methods.

Spam Review Detection Using the Linguistic and Spammer Behavioral Methods

Online reviews regarding different products or services have become the main source to determine public opinions. Consequently, manufacturers and sellers are extremely concerned with customer reviews as these have a direct impact on their businesses. Unfortunately, to gain profits or fame, spam reviews are written to promote or demote targeted products or services. This practice is known as review spamming. In recent years, the spam review detection problem has gained much attention from communities and researchers, but still there is a need to perform experiments on real-world large-scale review datasets. This can help to analyze the impact of widespread opinion spam in online reviews. In this work, two different spam review detection methods have been proposed: (1) Spam Review Detection using Behavioral Method (SRD-BM) utilizes thirteen different spammer's behavioral features to calculate the review spam score which is then used to identify spammers and spam reviews, and (2) Spam Review Detection using Linguistic Method (SRD-LM) works on the content of the reviews and utilizes transformation, feature selection and classification to identify the spam reviews. Experimental evaluations are conducted on a real-world Amazon review dataset which analyze 26.7 million reviews and 15.4 million reviewers. The evaluations show that both proposed models have significantly improved the detection process of spam reviews. Specifically, SRD-BM achieved 93.1% accuracy whereas SRD-LM achieved 88.5% accuracy in spam review detection. Comparatively, SRD-BM achieved better accuracy because it works on utilizing rich set of spammers behavioral features of review dataset which provides in-depth analysis of spammer behaviour. Moreover, both proposed models outperformed existing approaches when compared in terms of accurate identification of spam reviews. To the best of our knowledge, this is the first study of its kind which uses large-scale review dataset to analyze different spammers' behavioral features and linguistic method utilizing different available classifiers.

An enhanced feature‐based sentiment analysis approach

AbstractIn the last few years, online reviews where individuals express their thoughts, interests, experiences, and opinions have broadly spread over the internet. Sentiment analysis has evolved to analyze these online reviews and provide valuable insights for both individuals and organizations that may help them in making decisions. Unfortunately the performance of sentiment analysis process is affected by the nature of online reviews' content that may contain emoticons and negation words. Moreover, spam reviews have been written for the purpose of deceiving others. Therefore, there is a need to develop an approach that considers these issues. In this paper, an enhanced approach for sentiment analysis is proposed which aims to enhance the performance of classifying reviews based on their features and assigning accurate sentiment score to features. This enhanced approach is achieved by handling negation, detecting emoticons, and detecting spam reviews using a combination of different types of properties which leads to achieving better predictive performance. The proposed approach has been verified against three datasets of different sizes. The results indicate that the proposed approach achieves a maximum accuracy of about 99.06% in detecting spam reviews and a maximum accuracy of about 97.13% in classifying reviews.This article is categorized under: Algorithmic Development > Text Mining Technologies > Classification Technologies > Machine Learning

Detecting Online Spams through Supervised Learning Techniques

With more customers utilizing on the online review surveys to educate their administration basic leadership, assessment of reviews which economically affect the reality of organizations. Obviously, crafty people or gatherings have endeavored to manhandle or control online review spam to make benefits, etc, and that tricky recognition and counterfeit sentiment surveys is a subject of continuous research intrigue. In this paper, we clarify how supervised learning strategies are utilized to recognize online spam review surveys, preceding showing its utility utilizing an informational index of lodging reviews.